Results for “rev-ai”

Generates and maintains project documentation: Google-style docstrings, README, architecture docs, and ADRs, with a mandatory post-task review gate to keep docs current.

Audits a wiki for contradictions, stale content, orphan pages, duplicates, missing sections, broken wikilinks, and AI-tell contamination, producing a lint report for human review.

Use before delivering any documentation to validate quality, accuracy, and completeness. This skill provides a checklist for reviewing all documentation deliverables to ensure they meet minimum quality standards before distribution.

Write competitive research proposals for NSF, NIH, DOE, DARPA, and Taiwan NSTC with agency-specific formatting, review criteria, budget preparation, and compliance guidance.

Comprehensive guide to prevent unmaintainable code, especially from AI generation. Covers code duplication, documentation, error handling, naming conventions, architecture, performance, dependencies, modularity, testing, and technical debt prevention. Essential for code reviews and ensuring long-term code health.

Resolves an approved article comment task into a publishable AI markdown reply by fetching article context from a local HTTP API (with sf-cli fallback), reasoning with the selected quote and full article content, and writing the final reply to a backend-provided local result file path.

Detects and eliminates AI writing tropes that make text sound artificial or formulaic. Use when generating text content, writing documentation, creating code comments, or reviewing writing style. Supports four-tier JSON preferences (global/project x shared/local office.json) read via load-preferences.sh.

Remove signs of AI-generated writing from academic medical papers. Use when editing or reviewing manuscripts to make them sound more natural and professionally written. Based on Wikipedia's "Signs of AI writing" guide, adapted for medical literature. Detects and fixes patterns including: inflated significance claims, superficial -ing analyses, vague attributions, AI vocabulary words, copula avoidance, excessive hedging, generic conclusions, informal word choices (linked/beyond/via/where/yield), overly assertive causal claims, and artificially condensed expressions. Preserves legitimate academic transitions (Notably, Prior studies have shown, etc.).

Reverse-lookup glossary that turns a vague description of a web animation or motion effect into its exact term, helping users name effects for prompting AI or designers.

Look up current research and scientific information across three backends: fast web search, deep multi-source synthesis, and scholarly paper searches. Automatically routes each query to the best backend and saves every result for reproducible citation.

Verify whether an online bounty, freelance task, agent marketplace job, hackathon prize, or crypto work offer is actually open, accessible, and credibly funded. Use when evaluating task URLs, payout claims, escrow or treasury evidence, eligibility restrictions, payment history, expected value, or whether a claimed amount may be counted as real revenue.